SEARCH · Search PubMed

Results for “Ensemble learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources

PubMed2026

Dynamic evolution of chaperone-mediated autophagy is associated with tumor microenvironment remodeling and prognostic stratification in lung adenocarcinoma: insights from single-cell transcriptomics, ensemble machine learning, and experimental validation.

BACKGROUND: Lung adenocarcinoma (LUAD) shows prognostic heterogeneity, and tumor-node-metastasis (TNM) staging is limited for individualized management. Chaperone-mediated autophagy (CMA) maintains proteostasis, but its role during adenocarcinoma in situ (AIS)-minimally invasive adenocarcinoma (MIA)-invasive adenocarcinoma (IAC) progression remains unclear. METHODS: Single-cell RNA sequencing (scRNA-seq) data from GSE189357 and bulk transcriptomes from The Cancer Genome Atlas (TCGA)-LUAD and Gene Expression Omnibus (GEO) cohorts were integrated. CMA activity, cell-cell communication, weighted gene co-expression network analysis (WGCNA), tumor-normal differential expression, machine-learning survival modeling, tumor microenvironment (TME) features, drug sensitivity, and EPC1 function were analyzed. RESULTS: CMA-high tumor epithelial cells increased from AIS (58.1%) to MIA (65.7%) but declined in IAC (44.4%; p < 0.001). CMA-low cells preferentially received fibroblast-derived extracellular matrix cues. A CMA-negatively correlated module identified 69 core genes. Random survival forest (RSF) performed best among 117 machine-learning combinations (mean concordance index > 0.873). High-risk patients had worse survival across cohorts, and the risk score was independently associated with overall survival (hazard ratio = 16.013, 95% confidence interval: 9.579-26.768, p < 0.001). High-risk tumors showed proliferative activation and M0 macrophage enrichment, whereas low-risk tumors showed stronger immune-related signaling. EPC1 overexpression suppressed malignant phenotypes in A549 cells. CONCLUSION: CMA dynamics are associated with stromal and immune remodeling during LUAD progression. A CMA-based model provides robust prognostic stratification and may offer a basis for future TME-guided studies.

Chaperone-mediated autophagy↗

PubMed2025

The Effect of Alcohol Intake on Brain White Matter Microstructural Integrity: A New Causal Inference Framework for Incomplete Phenomic Data.

Although substance use, such as alcohol intake, is known to be associated with cognitive decline during aging, its direct influence on the central nervous system remains incompletely understood. In this study, we investigate the influence of alcohol intake frequency on reduction of brain white matter microstructural integrity in the fornix, a brain region considered a promising marker of age-related microstructural degeneration, using a large UK Biobank (UKB) cohort with extensive phenomic data reflecting a comprehensive lifestyle profile. Two major challenges arise: (a) potentially nonlinear confounding effects from phenomic variables and (b) a limited proportion of participants with complete phenomic data. To address these challenges, we develop a novel ensemble learning framework tailored for robust causal inference and introduce a data integration step to incorporate information from UKB participants with incomplete phenomic data, improving estimation efficiency. Our analysis reveals that daily alcohol intake may significantly reduce fractional anisotropy, a neuroimaging-derived measure of white matter structural integrity, in the fornix and increase systolic and diastolic blood pressure levels. Moreover, extensive numerical studies demonstrate the superiority of our method over competing approaches in terms of estimation bias, while outcome regression-based estimators may be preferred when minimizing mean squared error is prioritized. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Brain aging↗

PubMed2026

Beyond predictive performance: A systematic review and critical methodological appraisal of AI/ML and conventional modelling strategies in breast, colorectal, and pancreatic Cancer.

BACKGROUND: Predictive modelling for cancer risk, treatment-related complications, and survival is central to precision oncology. Conventional logistic regression (LR) and Cox proportional hazards (CoxPH) regression remain widely used but are limited when modelling nonlinear interactions, high-dimensional imaging features, and multimodal clinical-metabolic predictors. Artificial intelligence (AI) and machine learning (ML) methods offer expanded capability through automated feature extraction, ensemble learning, and flexible survival modelling, but the evidence on when AI/ML adds value over conventional models across cancer sites and predictive tasks remains fragmented. OBJECTIVE: To systematically evaluate the methodological performance, validation strategies, and translational limitations of AI/ML models compared with conventional statistical models in published predictive-modelling studies for breast, colorectal, or pancreatic cancer. METHODS: PubMed, Scopus, and Web of Science were searched for studies published between January 2019 and March 2025. Two reviewers independently conducted title-and-abstract screening, full-text eligibility assessment, and PROBAST risk-of-bias assessment. Sixty-five studies (n = 907,567 participants) were narratively synthesised by cancer site, predictive task, model family, comparator, validation strategy, predictor modality, and calibration or explainability reporting. RESULTS: The 65 studies comprised breast cancer (n = 35), colorectal cancer (n = 21), and pancreatic cancer (n = 9). AI/ML superiority over LR and CoxPH was task- and data-dependent. CNN- and U-Net-based models predominated in imaging and body-composition tasks, tree-based ensembles consistently outperformed LR for tabular perioperative complication prediction, and CoxPH remained competitive, and in the largest pancreatic risk study, superior to XGBoost (C-index 0.802 vs 0.723) in well-structured datasets. PROBAST analysis-domain risk was moderate in 54 of 65 studies (83%), driven by limited external validation, sparse calibration reporting (11/65), and few decision-curve analyses (7/65). CONCLUSION: AI/ML adds the most methodological value in imaging-derived feature extraction and nonlinear perioperative prediction, while conventional regression remains preferable in large, structured datasets with linear predictors. Clinical translation requires standardised body-composition definitions, external validation, calibration assessment, decision-curve analysis, and explainability, in line with TRIPOD+AI and CLAIM standards.

Humans↗

PubMed2026

Development and external validation of an explainable machine learning model for predicting chronic kidney disease progression in the Korean population.

BACKGROUND: Current risk stratification models, such as the Kidney Failure Risk Equation (KFRE), exhibit variable performance across ethnic groups and fail to capture dynamic clinical trajectories. This study aimed to develop and validate a Korean-specific machine learning (ML) model for predicting chronic kidney disease (CKD) progression using an ensemble approach. METHODS: We used electronic health records from Seoul National University Hospital for model development (n = 28,209) and the Korean Genome and Epidemiology Study (KoGES) CKD cohort for external validation (n = 3,960). The primary outcome was a composite of ≥40% decline in estimated glomerular filtration rate (eGFR) or progression to end-stage renal disease within 2 years. A soft-voting ensemble of four ML algorithms (XGBoost, LightGBM, CatBoost, and Random Forest) was developed. RESULTS: The ensemble model demonstrated robust discrimination in internal validation (area under the receiver operating characteristic curve [AUROC], 0.939; 95% confidence interval [CI], 0.934-0.944), significantly exceeding the KFRE (AUROC, 0.879-0.884). External validation in the KoGES cohort showed comparable discrimination (AUROC, 0.859; 95% CI, 0.798-0.914) versus KFRE (four-variable AUROC, 0.882; 95% CI, 0.818-0.935). Shapley Additive exPlanations (SHAP) analysis identified baseline eGFR, serum creatinine, eGFR slope, albumin, and hemoglobin as key prognostic features, supporting a complementary framework using KFRE for community screening and the ML model for hospital-based risk stratification. CONCLUSION: The ensemble ML model accurately predicts short-term CKD progression in Korean patients. By incorporating longitudinal features and ensemble learning, it provides a precise alternative to Western-derived equations, particularly in tertiary care settings.

Chronic kidney failure↗

PubMed2025

Gene Specific Pathogenicity Predictor for Chromatin-Remodeling BAF Complex-Associated Neurodevelopmental Disorders.

Advancements in whole genome sequencing have increased the number of variants of uncertain significance (VUS) identified in patient genomes. This has created a diagnostic bottleneck for genetic counselors tasked with sifting through these variants and determining those most likely to be causative for a patient's clinical presentation. Machine learning (ML) tools can aid in identifying pathogenic variants from VUS, but there is a need for gene-specific algorithms that predict pathogenic variants with high accuracy. To address this need, we present a workflow for developing gene-specific, ensemble-learning ML tools, that leverage outputs from other algorithms, locations of variants within the gene, and evolutionary conservation data to make a prediction of pathogenicity. Variants in SMARCA2 and SMARCA4 that are associated with rare neurodevelopmental diseases were used to screen 15 ML algorithms. A random forest learner was tuned to yield a final accuracy of 0.93 on holdout data. Generalizing this predictor to other BAF complex proteins resulted in a sharp decline in performance. We trained a final predictor for all genes in the study to create a predictor that identifies pathogenic variants in these BAF subunits with an accuracy of 0.91 on holdout data. This predictor specific to BAF complex proteins performs with higher accuracy and AUROC than any other predictor. The decline in performance when generalized to other proteins emphasizes the need for the gene-specific calibration of predictors. Our workflow for the development of such models provides a quick, computationally inexpensive route for improving the ML tools available to genetic counselors.

Journal Article↗

PubMed2026

Reinforcement learning-based dynamic ensemble for missense variant effect prediction and tiered prioritization of VUS.

BACKGROUND: Accurate classification of missense variants remains a challenging task despite major advances in genomics. Numerous computational models have been developed to assist in variant classification, but often require repeated integration and benchmarking efforts. Ensemble methods have been proposed to overcome the limitations of single predictors, but mostly rely on fixed, predefined weights that constrain their ability to capture interactions among predictive signals. METHODS: We present GenixRL, a dynamic ensemble framework that reformulates model fusion as a reinforcement learning optimization problem. GenixRL uses a Q-learning agent to learn a policy that dynamically weights the probabilistic outputs of complementary predictors, including BayesDel (addAF and noAF), ClinPred, and MetaRNN. Replacing static weighting with policy learning allows GenixRL to adaptively identify optimal weightings and substantially improve classification accuracy. RESULTS: In benchmark evaluation against 25 state-of-the-art predictors, GenixRL achieved an AUROC of 0.9644 on an independent ClinVar dataset. On saturation genome editing assays for BRCA1 and BRCA2, GenixRL achieved the best performance and ranked highest on 14 of 17 clinically significant genes in a zero-shot evaluation. Applied to uncertain and conflicting ClinVar variants, GenixRL enabled tiered, evidence-based prioritization of hundreds of thousands of variants as likely pathogenic or pathogenic with high confidence, supported by orthogonal population evidence from gnomAD. CONCLUSION: GenixRL advances pathogenicity prediction for missense variants and provides an adaptive ensemble that sorts variants of uncertain significance into tiered candidates for expert curation and functional validation.

Mutation, Missense↗

PubMed2024

PredIL13: Stacking a variety of machine and deep learning methods with ESM-2 language model for identifying IL13-inducing peptides.

Interleukin (IL)-13 has emerged as one of the recently identified cytokine. Since IL-13 causes the severity of COVID-19 and alters crucial biological processes, it is urgent to explore novel molecules or peptides capable of including IL-13. Computational prediction has received attention as a complementary method to in-vivo and in-vitro experimental identification of IL-13 inducing peptides, because experimental identification is time-consuming, laborious, and expensive. A few computational tools have been presented, including the IL13Pred and iIL13Pred. To increase prediction capability, we have developed PredIL13, a cutting-edge ensemble learning method with the latest ESM-2 protein language model. This method stacked the probability scores outputted by 168 single-feature machine/deep learning models, and then trained a logistic regression-based meta-classifier with the stacked probability score vectors. The key technology was to implement ESM-2 and to select the optimal single-feature models according to their absolute weight coefficient for logistic regression (AWCLR), an indicator of the importance of each single-feature model. Especially, the sequential deletion of single-feature models based on the iterative AWCLR ranking (SDIWC) method constructed the meta-classifier consisting of the top 16 single-feature models, named PredIL13, while considering the model's accuracy. The PredIL13 greatly outperformed the-state-of-the-art predictors, thus is an invaluable tool for accelerating the detection of IL13-inducing peptide within the human genome.

Humans↗

PubMed2026

Meta-PseU: A meta-classifier for robust prediction of RNA pseudouridine modification sites from long sequences.

BACKGROUND AND OBJECTIVES: Pseudouridine (Ψ) represents one of the most abundant and conserved RNA modifications. Ψ provides an additional hydrogen-bond donor that enhances RNA structural stability and modulates translation. It participates in diverse biological processes, including RNA-protein interactions, splicing, translational control, and stress responses. Aberrant pseudouridylation is implicated in cancer, neurodegenerative disorders, and autoimmune diseases. Despite its biological importance, experimental identification of Ψ sites remains time-consuming and costly, limiting the feasibility of transcriptome-wide profiling. Computational approaches have therefore become essential complements to experimental techniques. However, state-of-the-art machine-learning and deep-learning predictors often suffer from limited generalizability due to small training datasets. To overcome these issues, we aim at constructing new long-sequence datasets and developing a novel Ψ site predictor. METHODS: New long-sequence datasets were constructed as benchmarks for RNA Ψ-site prediction. The Ψ modification sites in RMBase 3.0 were mapped to the reference genomes across three species of human, mouse, and yeast, and the RNA sequences with a length of 201 were generated by extending the upstream and downstream from the mapped, central sites. To eliminate sequence redundancy, the sequences were clustered using CD-HIT with a 70% sequence identity threshold. We developed Meta-PseU, a logistic regression-based meta-classifier that considered 118 machine learning and deep learning classifiers. The datasets and programs are freely accessible at https://github.com/kuratahiroyuki/MetaPseU. RESULTS: By optimizing model configuration, we proposed the Meta-PseU model stacking 32 machine learning and deep learning classifiers out of 118 classifiers. Meta-PseU substantially improved model generalizability, overcoming a key limitation of existing approaches. It greatly outperformed state-of-the-art predictors and achieved increasing accuracy with increasing sequence length. CONCLUSIONS: Long-sequence datasets were newly constructed as benchmarks for RNA Ψ-site prediction. Meta-PseU offers a new framework for robust Ψ-site identification by using long sequences.

Pseudouridine↗

PubMed2026

Revealing potential biomarkers and metabolic mechanisms of ovarian aging in hens during late laying period based on machine learning and metabolomics.

Ovarian function decline during the late laying period represents a major bottleneck for the economic efficiency of the global poultry industry. However, the underlying metabolic mechanisms and reliable early-warning biomarkers for ovarian aging remain poorly understood. In this study, we performed the first untargeted LC-MS/MS metabolomics analysis of ovarian tissues from Taihe silky fowls at peak laying (30 weeks) and late laying (50 weeks) stages, and employed an ensemble machine learning strategy integrating LASSO, random forest, and support vector machine (SVM) algorithms to identify high-confidence core biomarkers of ovarian aging. Gene expression analysis was further conducted to validate the potential molecular mechanisms. Our results showed that the metabolic profiles of ovarian tissues differed significantly between the two groups. A total of 6 core biomarkers were identified, 4 of which were long-chain acylcarnitines. Mechanistic analysis revealed that downregulation of key genes in the carnitine shuttle system led to impaired mitochondrial fatty acid β-oxidation, which in turn triggered excessive oxidative stress and compromised ovarian endocrine function. In conclusion, this study identifies long-chain acylcarnitines as potential metabolic biomarkers for ovarian aging in Taihe silky fowls. These findings provide novel insights into the metabolic basis of poultry ovarian aging and lay a theoretical foundation for the precise regulation of reproductive performance in indigenous poultry breeds.

Animals↗

PubMed2025

In silico prediction method for plant Nucleotide-binding leucine-rich repeat- and pathogen effector interactions.

Plant Nucleotide-binding leucine-rich repeat (NLR) proteins play a crucial role in effector recognition and activation of Effector triggered immunity following pathogen infection. Genome sequencing advancements have led to the identification of a myriad of NLRs in numerous agriculturally important plant species. However, deciphering which NLRs recognize specific pathogen effectors remains challenging. Predicting NLR-effector interactions in silico will provide a more targeted approach for experimental validation, critical for elucidating function, and advancing our understanding of NLR-triggered immunity. In this study, NLR-effector protein complex structures were predicted using AlphaFold2-Multimer for all experimentally validated NLR-effector interactions reported in literature. Binding affinities- and energies were predicted using 97 machine learning models from Area-Affinity. We show that AlphaFold2-Multimer predicted structures have acceptable accuracy and can be used to investigate NLR-effector interactions in silico. Binding affinities for 58 NLR-effector complexes ranged between -8.5 and -10.6 log(K), and binding energies between -11.8 and -14.4 kcal/mol-1, depending on the Area-Affinity model used. For 2427 "forced" NLR-effector complexes, these estimates showed larger variability, enabling identification of novel NLR-effector interactions with 99% accuracy using an Ensemble machine learning model. The narrow range of binding energies- and affinities for "true" interactions suggest a specific change in Gibbs free energy, and thus conformational change, is required for NLR activation. This is the first study to provide a method for predicting NLR-effector interactions, applicable to all pathosystems. Finally, the NLR-Effector Interaction Classification (NEIC) resource can streamline research efforts by identifying NLRs important for plant-pathogen resistance, advancing our understanding of plant immunity.

Plant Proteins↗

PubMed2025

Noninvasive detection and differentiation of gastric malignancy using cell-free DNA biomarkers.

INTRODUCTION: Gastric cancer remains a major global health burden, with high mortality driven by late-stage diagnoses that limit treatment options and reduce survival. Current diagnostic methods such as endoscopy and biopsy are invasive, resource-intensive, and impractical for large-scale early detection. OBJECTIVES: This study aimed to develop and validate an ensemble machine learning model integrating four cell-free DNA (cfDNA) fragmentomic feature classes derived from 5 × whole genome sequencing (WGS) data to non-invasively differentiate malignant gastric cancer from benign gastric lesions in high-risk or symptomatic patients. METHODS: A total of 681 plasma samples were prospectively collected, comprising 329 from patients with gastric cancer or high-grade intraepithelial neoplasia (HGIN) and 352 from individuals with benign gastric conditions. The dataset was divided into a training cohort (n = 333) and a temporally independent validation cohort (n = 348). An external validation cohort of 305 participants was also included. RESULTS: The ensemble model achieved an AUROC of 0.920 in cross-validation testing on the training cohort, 0.912 in the independent validation cohort, and 0.896 (95% CI 0.860-0.932) in the external cohort. At a pre-specified prediction threshold of 0.402, the model demonstrated 93.3% sensitivity and 71.9% specificity in the validation cohort, yielding a PPV of 71.3% and an NPV of 93.5%. In the external cohort, sensitivity and specificity were 91.7% and 69.1%, respectively (PPV 75.7%, NPV 88.8%). Model scores correlated with clinical stage, tumor grade, and histopathological subtype. Approximately 71% of non-cancer patients could have been spared unnecessary endoscopy. CONCLUSIONS: The cfDNA fragmentomics-based ensemble model enables accurate, non-invasive differentiation between gastric cancer and benign gastric lesions in high-risk or symptomatic patients. This approach demonstrates strong potential as a pre-endoscopy triage tool, supporting earlier detection and more efficient use of diagnostic resources.

Humans↗

PubMed2025

Metagenomic analyses reveal E. coli-derived siderophores as potential signatures for breast cancer.

BACKGROUND: Breast cancer remains a leading cause of cancer-related mortality in women. Recent evidence implicates the gut microbiome and metabolites in breast cancer pathogenesis. This study explores associations between gut microbial species, their predicted metabolites, and breast cancer to uncover potential mechanistic insights. METHODS: Comprehensive metagenomic analyses were conducted on the gut microbiome of pre- and postmenopausal breast cancer patients, where microbial species were profiled through AMPHORA2 and metabolites were predicted through antiSMASH. Multivariate association analysis was used to identify significant associations between specific microbial species, predicted metabolites, and breast cancer status. A custom ensemble machine learning classifier was developed to classify pre- and postmenopausal breast cancer cases and controls based on microbial and predicted metabolite features. Additionally, a synthetic microbiome dataset was generated through MIDASim to validate the reproducibility of the ML results. Using our results, we explored the underlying dynamics of identified taxa and metabolite in breast cancer through literature and statistical support. RESULTS: Our analysis identified 471 microbial species and predicted 40 key metabolites in the metagenomic data. Multivariate analysis identified significant positive associations (p-value < 0.05) of E. coli, siderophore, and thiopeptide with breast cancer. The custom ensemble model achieved accuracy and AUC as high as 78% and 90%, respectively, in classifying pre- and postmenopausal cases and controls. The high-ranking features i.e., E. coli, siderophore, and thiopeptide were consistent with the results of the multivariate association analysis, thereby substantiating their biological significance. Using these findings, we propose a mechanistic model in which E. coli secretes siderophores under iron-limited conditions in breast cancer patients, for iron sequestration from the host, which can potentially promote angiogenesis and tumor progression. CONCLUSION: Our findings suggest that microbial iron acquisition mechanisms may play a critical role in breast cancer pathophysiology. Functional validation of these mechanisms is needed to assess therapeutic potential. This study highlights gut microbiota and their metabolites as promising targets for breast cancer research and intervention.

Breast Neoplasms↗

PubMed2026

Firemaster 550 differentially alters gene expression underlying synaptic function in amygdala of prairie voles after gestational or lactational exposure.

Neurodevelopmental disorders often share similar behavioral diagnostic criteria including socioemotional and cognitive deficits. The prairie vole is a uniquely suitable model to study these deficits because they demonstrate strong social affiliation, bi-parental care, and partner attachment. Previously, we have shown that developmental exposure to the flame-retardant mixture Firemaster 550 (FM 550) impairs socioemotional behavior in the prairie vole and alters underlying neuroanatomy and function. However, the mechanisms for impaired pair bonding in males and increased anxiety in females remain unknown, along with the specific critical window(s) of vulnerability. Herein, we exposed prairie vole dams to FM 550 during gestation or lactation, and performed bulk RNA-seq on the amygdala, a hub of socioemotional processing, in their adult offspring. Two mathematically orthogonal methods were utilized for analysis, a linear statistical method and an ensemble machine learning method, incorporating sex as a biological variable. Gene ontology (GO) pathway analysis was performed following both and results compared to identify potential mechanisms of toxicity. GO results indicated consistent expression changes in the Synapse cellular component in all conditions, and implicated glutamatergic signaling specifically. Additionally, gestational exposure (GE) altered genes underlying modulation of synaptic transmission and neural development, while lactational exposure (LE) impacted genes underlying synaptic plasticity, axon guidance, and mitophagy. Machine learning identified disruption of endocrine system development, regulation of biosynthetic processes in GE animals, and suppression of various neuroinflammatory genes across multiple groups. Finally, we performed RNA expression analysis using Nanostring and demonstrated stronger correlation with the differentially expressed genes (DEG) of interest in females than males. Overall, this study demonstrates both the intersecting and distinct impacts of FM 550 exposure on amygdalar gene expression depending on sex and timing of exposure.

Animals↗

PubMed2025

A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits.

BACKGROUND: DNA methylation (DNAm) provides a window to characterize the impacts of environmental exposures and the biological aging process. Epigenetic clocks are often trained on DNAm using penalized regression of CpG sites, but recent evidence suggests potential benefits of training epigenetic predictors on principal components. METHODOLOGY/FINDINGS: We developed a pipeline to simultaneously train three epigenetic predictors; a traditional CpG Clock, a PCA Clock, and a SuperLearner PCA Clock (SL PCA). We gathered publicly available DNAm datasets to generate i) a novel childhood epigenetic clock, ii) a reconstructed Hannum adult blood clock, and iii) as a proof of concept, a predictor of polybrominated biphenyl exposure using the three developmental methodologies. We used correlation coefficients and median absolute error to assess fit between predicted and observed measures, as well as agreement between duplicates. The SL PCA clocks improved fit with observed phenotypes relative to the PCA clocks or CpG clocks across several datasets. We found evidence for higher agreement between duplicate samples run on alternate DNAm arrays when using SL PCA clocks relative to traditional methods. Analyses examining associations between relevant exposures and epigenetic age acceleration (EAA) produced more precise effect estimates when using predictions derived from SL PCA clocks. CONCLUSIONS: We introduce a novel method for the development of DNAm-based predictors that combines the improved reliability conferred by training on principal components with advanced ensemble-based machine learning. Coupling SuperLearner with PCA in the predictor development process may be especially relevant for studies with longitudinal designs utilizing multiple array types, as well as for the development of predictors of more complex phenotypic traits.

DNA Methylation↗

PubMed2026

Social disconnection integrates genetic and proteomic risks in suicidal ideation and depression.

Suicidal ideation (SI) and major depressive disorder (MDD) are complex psychiatric conditions arising from the interplay of genetic liability, molecular processes, and psychosocial factors. While these dimensions have been extensively studied in isolation, their joint contribution to SI and MDD remains unclear. This study integrates multi-modal data to elucidate these synergistic effects and develop robust models for individual-level risk stratification. Leveraging longitudinal multi-modal data from 13,085 UK Biobank participants, we integrated genomic, proteomic, and social connection profiles. We developed interpretable risk scores using a rigorous supervised machine learning framework encompassing diverse linear and ensemble classifiers. Permutation importance was employed to quantify feature contributions and derive transparent, weighted risk metrics across diverse classifiers. These scores were validated through association, interaction, and mediation analyses. Social connection-based risk scores significantly differentiated cases and controls across the two suicidal ideation phenotypes at 2017 and 2023 with cross-sectional analyses (AUCs: 0.70 - 0.73), outperforming proteomic-only models. Functional dimensions of social connection emerged as the most informative predictors. Longitudinal analyses revealed that social risk scores at baseline predicted suicidal ideation onset six years later, independent of demographic covariates. Interaction analyses demonstrated that polygenic risk for suicide attempt significantly interacted with both social and proteomic risk features in relation to depression. Structural equation models further confirmed that social disconnection acts as a key mediator linking genetic predisposition to MDD and SI. Social disconnection is a critical risk factor mediating the impact of genetic vulnerability on psychiatric outcomes. Integrating social, genetic, and molecular data supports a multilevel framework for risk stratification and highlights the potential of socially oriented interventions to mitigate biological risk.

Humans↗

PubMed2026

Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions.

High-risk subtypes of invasive lung adenocarcinoma (IAC), particularly micropapillary- or solid-predominant patterns, are closely associated with poor prognosis. This multicenter retrospective study developed and validated a predictive model for the preoperative identification of these high-risk subtypes using topologically distinct intratumoral heterogeneity (ITH) scores derived from CT images. The study included 1,051 patients with IAC. Two complementary ITH scores were developed: a two-dimensional ITH score, which integrated local radiomics features with global pixel distribution patterns on the largest cross-sectional CT slice, and a three-dimensional ITH score, which extended this quantification across the entire tumor volume. Clinicoradiological features and ITH scores were incorporated as model inputs to construct six base machine learning classifiers and a final stacking ensemble classifier. Model interpretability and robustness were evaluated using SHapley Additive exPlanations (SHAP)-based ablation analyses. An independent dataset from The Cancer Imaging Archive (TCIA) was used for external validation to investigate associations between ITH scores and pathological characteristics, genomic features, recurrence-free survival, and overall survival. The stacking ensemble classifier achieved the best predictive performance, with an area under the receiver operating characteristic curve of 0.875, outperforming models based solely on radiomics features (0.834) or clinicoradiological features (0.792). SHAP analysis identified the 3D ITH score as the most influential contributor to model output, and TCIA validation showed that higher 3D ITH scores were associated with more aggressive tumor biology and poorer survival outcomes. The topologically distinct 3D ITH score may provide a clinically meaningful imaging biomarker for preoperative risk stratification in IAC.

Journal Article↗

PubMed2026

Investigating cross-organism prediction of prokaryotic essential proteins using unsupervised language model and ensemble strategy.

Cross-organism prediction of essential proteins is a critical task for drug discovery and microbial engineering, yet the generalizability of existing machine learning models across diverse species remains a significant challenge. In this study, we propose DeepPEP, a large language model-based framework designed to reliably transfer essential protein annotations between distantly related organisms. Utilizing 66 curated prokaryotic datasets, we systematically evaluated DeepPEP's cross-organism performance under various conditions. Initial pairwise predictions revealed a correlation between performance and evolutionary distance; however, further investigation demonstrated that integrating training data from multiple organisms yields superior predictive power. In a benchmark scenario designed to simulate real-world applications, DeepPEP outperformed the state-of-the-art tool Geptop 2.0, showcasing a robust ability to identify species-specific essential proteins. Finally, a case study on novel genomes confirmed the model's practical effectiveness. Our results suggest that DeepPEP is a powerful strategy for prokaryotic essential protein prediction, and the rigorous evaluation framework established in this study provides a new benchmark for the field.

Large Language Models↗

PubMed2026

Linking MRI radiomics to transcriptomics-based radiosensitivity in lower-grade glioma: A radiogenomic framework.

BACKGROUND: RSI is a transcriptomics-based biomarker associated with radiotherapy outcomes, but its clinical application is constrained by the requirement for tumor tissue and RNA sequencing. This study investigates whether MRI-derived radiomic features can reflect RSI-defined intrinsic radiosensitivity in lower-grade glioma.This addresses a critical gap arising from the limited availability of matched imaging and genomic data in routine clinical practice. METHODS: MRI-derived radiomic features were extracted from FLAIR images of lower-grade glioma patients obtained from TCIA and matched with transcriptomic data from TCGA. A total of 107 patients with both MRI and RNA sequencing data were included in the radiogenomic analysis. Radiomic features were ranked using a Borda-based ensemble feature selection strategy. Five supervised machine-learning classifiers were trained to predict RSI-based radiosensitivity classification, and model interpretability was assessed using SHAP within radiogenomic framework. RESULTS: Classification performance increased with feature number and stabilized at compact subset of 13 radiomic features. Logistic regression showed stable performance with an AUC of 0.82 (95 % CI: 0.71-0.93). SHAP analysis indicated that heterogeneity-related texture features were dominant contributors to model predictions, with many associated with the RR phenotype, while others were linked to the RS phenotype. CONCLUSION: An MRI-based radiomic signature enables non-invasive prediction of RSI-defined radiosensitivity in lower-grade glioma. Rather than offering an immediately deployable clinical tool, this study establishes a proof-of-concept radiogenomic framework demonstrating that intrinsic radiosensitivity, traditionally assessed through invasive molecular assays, can be approximated using quantitative imaging features. These findings highlight the potential of imaging-based radiosensitivity assessment and provide a foundation for future radiogenomic investigations.

Lower-grade glioma↗